CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

• URL: http://arxiv.org/abs/2411.12768v2
• Date: Wed, 11 Jun 2025 12:40:14 GMT
• Title: CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
• Authors: Nay Myat Min, Long H. Pham, Yige Li, Jun Sun,
• Abstract summary: Large Language Models (LLMs) are vulnerable to backdoor attacks that manipulate outputs via hidden triggers.<n>We propose Internal Consistency Regularization (CROW), a defense leveraging the observation that backdoored models exhibit unstable layer-wise hidden representations when triggered.<n>CROW enforces consistency across layers via adversarial perturbations and regularization during finetuning, neutralizing backdoors without requiring clean reference models or trigger knowledge--only a small clean dataset.
• Score: 7.282200564983221
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are vulnerable to backdoor attacks that manipulate outputs via hidden triggers. Existing defense methods--designed for vision/text classification tasks--fail for text generation. We propose Internal Consistency Regularization (CROW), a defense leveraging the observation that backdoored models exhibit unstable layer-wise hidden representations when triggered, while clean models show smooth transitions. CROW enforces consistency across layers via adversarial perturbations and regularization during finetuning, neutralizing backdoors without requiring clean reference models or trigger knowledge--only a small clean dataset. Experiments across Llama-2 (7B, 13B), CodeLlama (7B, 13B), and Mistral-7B demonstrate CROW's effectiveness: it achieves significant reductions in attack success rates across diverse backdoor strategies (sentiment steering, targeted refusal, code injection) while preserving generative performance. CROW's architecture-agnostic design enables practical deployment.

Related papers

• Backdoor Cleaning without External Guidance in MLLM Fine-tuning [76.82121084745785]
  Believe Your Eyes (BYE) is a data filtering framework that leverages attention entropy patterns as self-supervised signals to identify and filter backdoor samples.<n>It achieves near-zero attack success rates while maintaining clean-task performance.
  arXiv  Detail & Related papers  (2025-05-22T17:11:58Z)
• Backdoor Defense in Diffusion Models via Spatial Attention Unlearning [0.0]
  Text-to-image diffusion models are increasingly vulnerable to backdoor attacks.<n>We propose Spatial Attention Unlearning (SAU), a novel technique for mitigating backdoor attacks in diffusion models.
  arXiv  Detail & Related papers  (2025-04-21T04:00:19Z)
• ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models [55.93380086403591]
  Generative large language models are vulnerable to backdoor attacks.<n>$textitELBA-Bench$ allows attackers to inject backdoor through parameter efficient fine-tuning.<n>$textitELBA-Bench$ provides over 1300 experiments.
  arXiv  Detail & Related papers  (2025-02-22T12:55:28Z)
• REFINE: Inversion-Free Backdoor Defense via Model Reprogramming [60.554146386198376]
  Backdoor attacks on deep neural networks (DNNs) have emerged as a significant security threat. We propose REFINE, an inversion-free backdoor defense method based on model reprogramming.
  arXiv  Detail & Related papers  (2025-02-22T07:29:12Z)
• Boosting Graph Robustness Against Backdoor Attacks: An Over-Similarity Perspective [5.29403129046676]
  Graph Neural Networks (GNNs) have achieved notable success in tasks such as social and transportation networks.<n>Recent studies have highlighted the vulnerability of GNNs to backdoor attacks, raising significant concerns about their reliability in real-world applications.<n>We propose a novel graph backdoor defense method SimGuard.
  arXiv  Detail & Related papers  (2025-02-03T11:41:42Z)
• Neutralizing Backdoors through Information Conflicts for Large Language Models [20.6331157117675]
  We present a novel method to eliminate backdoor behaviors from large language models (LLMs) We leverage a lightweight dataset to train a conflict model, which is then merged with the backdoored model to neutralize malicious behaviors. We can reduce the attack success rate of advanced backdoor attacks by up to 98% while maintaining over 90% clean data accuracy.
  arXiv  Detail & Related papers  (2024-11-27T12:15:22Z)
• Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis [5.8634235309501435]
  We propose a backdoor defense framework tailored to object detection models. By quantifying and analyzing inconsistencies, we develop an algorithm to detect backdoors. Experiments with state-of-the-art two-stage object detectors show our method achieves a 90% improvement in backdoor removal rate.
  arXiv  Detail & Related papers  (2024-09-24T12:58:35Z)
• CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models [39.782217458240225]
  This paper presents CLIBE, the first framework to detect dynamic backdoors in Transformer-based NLP models. To the best of our knowledge, CLIBE is the first framework capable of detecting backdoors in text generation models without access to trigger input test samples.
  arXiv  Detail & Related papers  (2024-09-02T11:59:56Z)
• DeCE: Deceptive Cross-Entropy Loss Designed for Defending Backdoor Attacks [26.24490960002264]
  We propose a general and effective loss function DeCE (Deceptive Cross-Entropy) to enhance the security of Code Language Models. Our experiments across various code synthesis datasets, models, and poisoning ratios demonstrate the applicability and effectiveness of DeCE.
  arXiv  Detail & Related papers  (2024-07-12T03:18:38Z)
• Revisiting Backdoor Attacks against Large Vision-Language Models [76.42014292255944]
  This paper empirically examines the generalizability of backdoor attacks during the instruction tuning of LVLMs. We modify existing backdoor attacks based on the above key observations. This paper underscores that even simple traditional backdoor strategies pose a serious threat to LVLMs.
  arXiv  Detail & Related papers  (2024-06-27T02:31:03Z)
• BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models [57.5404308854535]
  Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. We present BEEAR, a mitigation approach leveraging the insight that backdoor triggers induce relatively uniform drifts in the model's embedding space. Our bi-level optimization method identifies universal embedding perturbations that elicit unwanted behaviors and adjusts the model parameters to reinforce safe behaviors against these perturbations.
  arXiv  Detail & Related papers  (2024-06-24T19:29:47Z)
• Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable [70.77600345240867]
  A novel arbitrary-in-arbitrary-out (AIAO) strategy makes watermarks resilient to fine-tuning-based removal. Unlike the existing methods of designing a backdoor for the input/output space of diffusion models, in our method, we propose to embed the backdoor into the feature space of sampled subpaths. Our empirical studies on the MS-COCO, AFHQ, LSUN, CUB-200, and DreamBooth datasets confirm the robustness of AIAO.
  arXiv  Detail & Related papers  (2024-05-01T12:03:39Z)
• BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning [85.2564206440109]
  This paper reveals the threats in this practical scenario that backdoor attacks can remain effective even after defenses. We introduce the emphtoolns attack, which is resistant to backdoor detection and model fine-tuning defenses.
  arXiv  Detail & Related papers  (2023-11-20T02:21:49Z)
• CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning [63.72975421109622]
  CleanCLIP is a finetuning framework that weakens the learned spurious associations introduced by backdoor attacks. CleanCLIP maintains model performance on benign examples while erasing a range of backdoor attacks on multimodal contrastive learning.
  arXiv  Detail & Related papers  (2023-03-06T17:48:32Z)
• Mitigating Backdoors in Federated Learning with FLD [7.908496863030483]
  Federated learning allows clients to collaboratively train a global model without uploading raw data for privacy preservation. This feature has recently been found responsible for federated learning's vulnerability in the face of backdoor attacks. We propose Federated Layer Detection (FLD), a novel model filtering approach for effectively defending against backdoor attacks.
  arXiv  Detail & Related papers  (2023-03-01T07:54:54Z)
• Backdoor Defense via Suppressing Model Shortcuts [91.30995749139012]
  In this paper, we explore the backdoor mechanism from the angle of the model structure. We demonstrate that the attack success rate (ASR) decreases significantly when reducing the outputs of some key skip connections.
  arXiv  Detail & Related papers  (2022-11-02T15:39:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.